Claude Skills

Templates and patterns for common ML training scenarios including text classification, text generation, fine-tuning, and PEFT/LoRA. Provides ready-to-use training configurations, dataset preparation scripts, and complete training pipelines. Use when building ML training pipelines, fine-tuning models, implementing classification or generation tasks, setting up PEFT/LoRA training, or when user mentions model training, fine-tuning, classification, generation, or parameter-efficient tuning.

Testbench verification best practices and patterns. This skill provides architecture guidance, verification methodology, and examples for writing professional-quality testbenches. Examples: "testbench best practices", "how to structure TB", "verification patterns"

Primary SystemVerilog orchestrator. Handles all RTL tasks end-to-end - routes to agents, runs verification, iterates until working. Examples: "create a FIFO", "test my UART", "fix lint errors", "implement and verify"

Summarize Verilator/lint output in a readable format

Cost estimation scripts and tools for calculating GPU hours, training costs, and inference pricing across Modal, Lambda Labs, and RunPod platforms. Use when estimating ML training costs, comparing platform pricing, calculating GPU hours, budgeting for ML projects, or when user mentions cost estimation, pricing comparison, GPU budgeting, training cost analysis, or inference cost optimization.

Supabase CMS integration patterns, schema design, RLS policies, and content management for Astro websites. Use when building CMS systems, setting up Supabase backends, creating content schemas, implementing RLS security, or when user mentions Supabase CMS, headless CMS, content management, database schemas, or Row Level Security.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Intent router and expand mode orchestrator for GateFlow. Classifies user intent semantically, determines confidence, triggers expand mode for ambiguous requests, and hands off to appropriate skill/agent.

Astro content collections setup, type-safe schemas, query patterns, and frontmatter validation. Use when building Astro sites, setting up content collections, creating collection schemas, querying content, validating frontmatter, or when user mentions Astro collections, content management, MDX content, type-safe content, or collection queries.

Mobile authentication patterns with Clerk, Supabase, and custom auth including biometrics, secure storage, and social login. Use when implementing authentication, managing tokens, or setting up biometric unlock.

React, MDX, and Tailwind CSS integration patterns for Astro websites. Use when adding React components, configuring MDX content, setting up Tailwind styling, integrating component libraries, building interactive UI elements, or when user mentions React integration, MDX setup, Tailwind configuration, component patterns, or UI frameworks.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Astro best practices, routing patterns, component architecture, and static site generation techniques. Use when building Astro websites, setting up routing, designing component architecture, configuring static site generation, optimizing build performance, implementing content strategies, or when user mentions Astro patterns, routing, component design, SSG, static sites, or Astro best practices.

SystemVerilog lint checker with structured output. Runs Verilator lint, categorizes errors/warnings, explains issues, returns parseable result block for orchestration.

SystemVerilog learning mode - generates exercises, reviews solutions

Expand mode - asks clarifying questions, presents options with trade-offs, then hands off to appropriate skill/agent with enriched context.

Parallel build orchestrator for SystemVerilog creation tasks. Decomposes designs into independent modules, builds in parallel phases, runs verification on each component, then integrates. Example: "/gf-build RISC-V CPU with ALU, regfile, decoder, control FSM"

AI-powered content and image generation using content-image-generation MCP with Google Imagen 3/4, Veo 2/3, Claude Sonnet, and Gemini 2.0. Use when generating marketing content, creating hero images, building blog posts, generating product descriptions, creating videos, optimizing AI prompts, estimating generation costs, or when user mentions Imagen, Veo, AI content, AI images, content generation, image generation, video generation, marketing copy, or Google AI.

Spawn and coordinate team-agents and orchestration patterns for parallel execution. Use for complex multi-component work.